Efficient Car Recognition Policies

Many tasks require an imaging system to identify an object, such as the type of a car; in many cases, it is critical to make this identification quickly, as well as accurately. This paper addresses the challenges of producing recognition systems that consider both of these objectives. In general, an “(recognition) policy” specifies when to apply which “imaging operators”, which can range from low-level edge-detectors and region-growers through high-level token-combination–rules and expectation-driven object-detectors. Given the costs of these operators and the distribution of possible images, we can determine both the expected cost and expected accuracy of any such policy. Our task is to find a maximally effective policy — typically one with sufficient accuracy, whose cost is minimal. We compare various ways to produce such policies in general, and show that policies that select the operators that maximize information gain per unit cost work effectively.